Corpus ID: 10315116

Learning from Rational Behavior: Predicting Solutions to Unknown Linear Programs

@inproceedings{Jabbari2016LearningFR,
  title={Learning from Rational Behavior: Predicting Solutions to Unknown Linear Programs},
  author={S. Jabbari and R. Rogers and A. Roth and S. Wu},
  booktitle={NIPS},
  year={2016}
}
  • S. Jabbari, R. Rogers, +1 author S. Wu
  • Published in NIPS 2016
  • Computer Science, Mathematics
  • We define and study the problem of predicting the solution to a linear program (LP) given only partial information about its objective and constraints. This generalizes the problem of learning to predict the purchasing behavior of a rational agent who has an unknown objective function, that has been studied under the name "Learning from Revealed Preferences". We give mistake bound learning algorithms in two settings: in the first, the objective of the LP is known to the learner but there is an… CONTINUE READING
    12 Citations

    Figures and Topics from this paper.

    Strategic Classification from Revealed Preferences
    • 38
    • PDF
    Grinding the Space: Learning to Classify Against Strategic Agents
    • 1
    • PDF
    Learning Market Parameters Using Aggregate Demand Queries
    • 7
    • PDF
    Learning and Reasoning With Constraints
    Learning Linear Programs from Data
    • 3
    Distinguishing Distributions When Samples Are Strategically Transformed
    • 4
    • PDF
    Learning SMT(LRA) Constraints using SMT Solvers
    • 18
    • PDF

    References

    SHOWING 1-10 OF 23 REFERENCES
    Learning Economic Parameters from Revealed Preferences
    • 35
    • PDF
    Efficiently Learning from Revealed Preference
    • 37
    • PDF
    Learning from revealed preference
    • 50
    Learning What's Going on: Reconstructing Preferences and Priorities from Opaque Transactions
    • 7
    • PDF
    Online Learning and Profit Maximization from Revealed Preferences
    • 23
    • PDF
    Optimal learners for multiclass problems
    • 26
    • PDF
    Learning Quickly When Irrelevant Attributes Abound: A New Linear-Threshold Algorithm
    • N. Littlestone
    • Mathematics
    • 28th Annual Symposium on Foundations of Computer Science (sfcs 1987)
    • 1987
    • 1,496
    • PDF
    Watch and learn: optimizing from revealed preferences feedback
    • 31
    • PDF
    Preference Learning
    • 235
    Preference Learning
    • 232
    • PDF